Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
imyzx2017 d8623c9e86 | 2 years ago | |
---|---|---|
gpt2-changing-gates-gifs | 2 years ago | |
src | 2 years ago | |
Masked_pangu_eachTask.py | 2 years ago | |
dataset_restore_data0.py | 2 years ago | |
gate_pruning_pangu.py | 2 years ago | |
grad_pangu_eachTask.py | 2 years ago | |
jieba-0.42.1.tar.gz | 2 years ago | |
ma-pre-start.sh | 2 years ago | |
readme.md | 2 years ago | |
sentencepiece-0.1.94-cp37-cp37m-linux_aarch64.whl | 2 years ago | |
task_05_CFT_Masked_inference.py | 2 years ago | |
tokenization_jieba.py | 2 years ago | |
utils_fix.py | 2 years ago |
「鹏程·盘古」在NPU服务器上的剪枝探索,在多头attention的head维度尝试了逐个head剪枝 / 全局随机剪枝 / 计算head_importance再剪枝的三种方法
[训练脚本]
华为NPU ASCEND 910A 一张,框架环境为mindspore-1.3
python task_05_CFT_Masked_inference.py
[逐个head剪枝]
修改TASK_METHOD=0
[逐个head剪枝]
修改TASK_METHOD=1
python grad_pangu_eachTask.py
[遍历数据集计算head重要性分数矩阵]
【根据head_importance生成mask配置】
python task_05_CFT_Masked_inference.py
修改TASK_METHOD=3
[head重要性剪枝]
支持在鹏城云脑2上,或NPU服务器上,进行盘古2.6B大模型剪枝实验
Python Shell
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》